Upload tokenizer
Browse files- special_tokens_map.json +2 -10
- tokenizer.json +0 -0
- tokenizer_config.json +2 -12
special_tokens_map.json
CHANGED
|
@@ -1,15 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"bos_token": "
|
| 3 |
-
"cls_token": "<s>",
|
| 4 |
"eos_token": "</s>",
|
| 5 |
-
"mask_token":
|
| 6 |
-
"content": "<mask>",
|
| 7 |
-
"lstrip": true,
|
| 8 |
-
"normalized": false,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false
|
| 11 |
-
},
|
| 12 |
"pad_token": "<pad>",
|
| 13 |
-
"sep_token": "</s>",
|
| 14 |
"unk_token": "<unk>"
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "</s>",
|
|
|
|
| 3 |
"eos_token": "</s>",
|
| 4 |
+
"mask_token": "<mask>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"pad_token": "<pad>",
|
|
|
|
| 6 |
"unk_token": "<unk>"
|
| 7 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,15 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"bos_token": "<s>",
|
| 4 |
"clean_up_tokenization_spaces": true,
|
| 5 |
-
"
|
| 6 |
-
"
|
| 7 |
-
"errors": "replace",
|
| 8 |
-
"mask_token": "<mask>",
|
| 9 |
-
"model_max_length": 1024,
|
| 10 |
-
"pad_token": "<pad>",
|
| 11 |
-
"sep_token": "</s>",
|
| 12 |
-
"tokenizer_class": "BartTokenizer",
|
| 13 |
-
"trim_offsets": true,
|
| 14 |
-
"unk_token": "<unk>"
|
| 15 |
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
| 2 |
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 4 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
}
|